Sumkin et al. showed that even without undergoing additional training, technologists classified screening mammograms at a reasonable level of accuracy [ 19].
The trial management system also classifies screening results (ultrasound findings and CA 125 concentrations) entered over the web browser, schedules appropriate follow-up appointments, and prints all letters to individual women.
We classified screening hits into two categories, i.e., off-target (OT -related and OT -relatedd, using sequence-bandd OTE prediction similar to DasGusinget al. [ 18] (see Additional file 1 for details).
Patients with DCIS that had been detected by screening mammography were classified as screen-detected patients, when the examination two years earlier failed to reveal an abnormality (n = 54).
Using the NCSP database, gastric cancer patients were classified by screening history in 2002 2007 (9191 never screened and 9977 ever screened).
Sedentary leisure activities were classified as screen based and non-screen based.
Cancers were classified as screen-detected if an abnormal screen led to a diagnostic sequence that resulted in the detection of a breast cancer.
In an attempt to understand the reason for screening being less effective in young women we also looked, by age group, at the proportion of cases classified as screen detected, prevalent, interval, never screened or lapsed and "after an abnormal smear result".
Of these 73 women, five had had no previous smear tests, 32 were classified as screen detected (13 on their first screen and 19 on subsequent tests), 15 as interval cancers (last result was normal), and in 21 the diagnosis followed a history of abnormal results (table 2).
In our previous study, we found that 82% of procedures designated as screening from the HCPCS codes would have been classified as screening from our algorithm [ 16].
